Research map / Graph learning / Knowledge and temporal graphs
ARNS: Adaptive Relation-Aware Negative Sampling with Curriculum Learning for Inductive Knowledge Graph Completion
Ling Ding, Zhizhi Yu, Di Jin, Lei Huang
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add L-WD and relation-graph negatives with adaptive curriculum instead of only random negatives (ablation) | ARNS · FB-100 | MRR: 0.131 -> 0.251 | Improved |
| add L-WD and relation-graph negatives with adaptive curriculum instead of only random negatives (ablation) | ARNS · NL-100 | MRR: 0.251 -> 0.293 | Improved |
| add L-WD negative sampling (ablation) | ARNS · FB-100 | MRR: 0.217 -> 0.251 | Improved |
| add relation-graph negative sampling (ablation) | ARNS · FB-100 | MRR: 0.211 -> 0.251 | Improved |
| add relation layer (ablation) | ARNS · FB-100 | MRR: 0.155 -> 0.251 | Improved |
| add sum aggregation (ablation) | ARNS · NL-100 | MRR: 0.211 -> 0.293 | Improved |
| add mean aggregation (ablation) | ARNS · FB-100 | MRR: 0.244 -> 0.251 | Improved |
| ARNS vs strongest baseline in fully inductive FB-100 | ARNS · FB-100 | MRR: 0.131 -> 0.251 | Improved |
| ARNS vs baselines on semi-inductive FB-50 | ARNS · FB-50 | MRR: 0.138 (GreenKGC) vs 0.123 | Hurt |
| ARNS vs NodePiece on traditional inductive NELL995-v1 | ARNS · NELL995-v1 | MRR: 0.672 (NodePiece) vs 0.637 | Hurt |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- InGram — InGram: Inductive Knowledge Graph Embedding via Relation Graphs (ICML 2023) · better on 8 of 8 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- Towards Global-Topology Relation Graph for Inductive Knowledge Graph Completion (AAAI 2025 · similarity 0.90)
- S²DN: Learning to Denoise Unconvincing Knowledge for Inductive Knowledge Graph Completion (AAAI 2025 · similarity 0.89)
- Replacing Paths with Connection-Biased Attention for Knowledge Graph Completion (AAAI 2025 · similarity 0.87)
- Stability and Generalization Capability of Subgraph Reasoning Models for Inductive Knowledge Graph Completion (ICML 2025 · similarity 0.87)
- Context-aware Inductive Knowledge Graph Completion with Latent Type Constraints and Subgraph Reasoning (AAAI 2025 · similarity 0.87)
- Toward a Unified Statistical Theory of Unsupervised Pretraining and Supervised Neural Knowledge Graph Learning (NeurIPS 2026 · similarity 0.86)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
